Atrous Convolution
Atrous Convolution is a convolutional operation in deep learning that belongs to the family of convolution variants and is distinguished by its use of a dilation rate to control the spacing between kernel elements, enabling increased receptive field coverage without sacrificing spatial resolution or requiring additional parameters.
251
Publications
52.9K
Citations
1.1K
Authors
388
Institutions
Publications per year
2017–2026
250
Parents
251
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 22.1K citations
Rethinking Atrous Convolution for Semantic Image Segmentation
Liang-Chieh Chen, George Papandreou, Florian Schroff et al. · arXiv (Cornell University) · 2017 · 7.5K citations · Full text
DenseASPP for Semantic Segmentation in Street Scenes
Maoke Yang, Kun Yu, Chi Zhang et al. · 2018 · 1.6K citations
1–5 of 251
1.1K
9
h-index
6
h-index
5
h-index
4
h-index
4
h-index
1–5 of 1.1K
388

Chinese Academy of Sciences
Beijing, China
19 h-index
82 publications
13.6K citations
University of Chinese Academy of Sciences
Beijing, China
13 h-index
36 publications
1.1K citations

Beihang University
Beijing, China
8 h-index
22 publications
769 citations

University of Electronic Science and Technology of China
Chengdu, China
7 h-index
29 publications
1.5K citations
Aerospace Information Research Institute
Beijing, China
7 h-index
20 publications
573 citations
Xiamen University
Xiamen, China
5 h-index
15 publications
2.2K citations
Dalian University of Technology
Dalian, China
4 h-index
12 publications
644 citations

Central South University
Changsha, China
4 h-index
22 publications
860 citations
1–8 of 388
21 publications · 1.4K citations
17
h-index
18 publications · 762 citations
16
h-index
Repository · 16 publications · 13.3K citations
13
h-index
7 publications · 361 citations
7
h-index
7 publications · 320 citations
6
h-index
1–5